DeepAI AI Chat

From Logical to Distributional Models

12/30/2014

∙

by Anne Preller, et al.

∙

∙

The paper relates two variants of semantic models for natural language, logical functional models and compositional distributional vector space models, by transferring the logic and reasoning from the logical to the distributional models. The geometrical operations of quantum logic are reformulated as algebraic operations on vectors. A map from functional models to vector space models makes it possible to compare the meaning of sentences word by word.

page 1

page 2

page 3

page 4

∙ 12/31/2010

Concrete Sentence Spaces for Compositional Distributional Models of Meaning

Coecke, Sadrzadeh, and Clark (arXiv:1003.4394v1 [cs.CL]) developed a com...

0 Edward Grefenstette, et al. ∙

∙ 08/29/2019

Feature2Vec: Distributional semantic modelling of human property knowledge

Feature norm datasets of human conceptual knowledge, collected in survey...

0 Steven Derby, et al. ∙

∙ 07/25/2017

Analogs of Linguistic Structure in Deep Representations

We investigate the compositional structure of message vectors computed b...

0 Jacob Andreas, et al. ∙

∙ 09/01/2017

Variational Inference for Logical Inference

Functional Distributional Semantics is a framework that aims to learn, f...

0 Guy Emerson, et al. ∙

∙ 07/20/2017

High-risk learning: acquiring new word vectors from tiny data

Distributional semantics models are known to struggle with small data. I...

0 Aurélie Herbelot, et al. ∙

∙ 05/12/2021

Conversational Negation using Worldly Context in Compositional Distributional Semantics

We propose a framework to model an operational conversational negation b...

0 Benjamin Rodatz, et al. ∙

∙ 08/15/2019

Vector spaces as Kripke frames

In recent years, the compositional distributional approach in computatio...

0 Giuseppe Greco, et al. ∙